PerTurbo manifold learning algorithm for weakly labelled hyperspectral image classification

Laëtitia Chapel (1) , Thomas Burger (2) , Nicolas Courty (1) , Sébastien Lefèvre (1)

1 OBELIX - Environment observation with complex imagery
2 BIG - Institut de Biosciences et de Biotechnologies de Grenoble (ex-IRTSV)

Hyperspectral data analysis has been given a growing attention due to the scientific challenges it raises and the wide set of applications that can benefit from it. Classification of hyperspectral images has been identified as one of the hottest topics in this context, and has been mainly addressed by discriminative methods such as SVM. In this paper, we argue that generative methods, and especially those based on manifold representation of classes in the hyperspectral space, are relevant alternatives to SVM. To illustrate our point, we focus on the recently published PerTurbo algorithm and benchmark against SVM this generative manifold learning algorithm in the context of hyperspectral image classification. This choice is motivated by the fact that PerTurbo is fitted with numerous interesting properties, such as low sensitivity to dimensionality curse, high accuracy in weakly labelled images classification context (few training samples), straightforward extension to on-line setting, and interpretability for the practitioner. The promising results call for an up-to-date interest toward generative algorithms for hyperspectral image classification.

Mots clés: Index Terms-Classification; remote sensing; hyperspectral im- ages; PerTurbo algorithm; generative method; manifold learning; Support Vector Machines; low-sized training sets

Domaines: Traitement des images [eess.IV]

Laëtitia Chapel, Thomas Burger, Nicolas Courty, Sébastien Lefèvre. PerTurbo manifold learning algorithm for weakly labelled hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, pp.1070-1078. ⟨10.1109/JSTARS.2014.2304304⟩. ⟨hal-00998258⟩